speak

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It explains the processing pipeline (resolving speaker, layering mood, applying overrides), return behavior (job_id or job_ids for variants), and side effects (timestamps sidecar). It also notes v3 audio tag support. Missing details about latency, cost, or failure modes, but sufficient for a generation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with a concise summary paragraph followed by a bulleted argument list. The first sentence is a punchy purpose statement, and each argument is described in one line. The length is justified for 13 parameters, but the 'engine / format' line could be more explicit.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 13-parameter tool with no output schema and no annotations, the description provides substantial context: return values, sidecar outputs, variants, and parameter precedence. The main gaps are the undocumented 'pronunciation' parameter and the indirect engine/format reference. Overall, it gives an agent enough information to use the tool correctly in most cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It explains speaker, text, mood, workspace, per-line overrides, variants, and timestamps. However, 'pronunciation' is completely omitted, and 'engine / format: as generate_speech' relies on external reference without inlining the semantics. Despite the gap, the description adds meaningful meaning to most parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Speak a line as a saved SPEAKER, optionally in a MOOD,' a specific verb-resource pairing that clearly identifies the tool's function. It distinguishes itself from siblings like generate_speech by emphasizing the use of a saved speaker, making the purpose immediately clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers clear contextual guidance, directing users to list_speakers for valid speaker names and noting that engine/format parameters follow generate_speech. It implies when to use this tool (when a saved speaker exists) but does not explicitly name alternatives like generate_dialogue or generate_speech as substitutes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.